yt_dlp/extractor/drooble.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     try_get,
   8 )
   9
  10
  11 class DroobleIE(InfoExtractor):
  12     _VALID_URL = r'''(?x)https?://drooble\.com/(?:
  13         (?:(?P<user>[^/]+)/)?(?P<kind>song|videos|music/albums)/(?P<id>\d+)|
  14         (?P<user_2>[^/]+)/(?P<kind_2>videos|music))
  15     '''
  16     _TESTS = [{
  17         'url': 'https://drooble.com/song/2858030',
  18         'md5': '5ffda90f61c7c318dc0c3df4179eb064',
  19         'info_dict': {
  20             'id': '2858030',
  21             'ext': 'mp3',
  22             'title': 'Skankocillin',
  23             'upload_date': '20200801',
  24             'timestamp': 1596241390,
  25             'uploader_id': '95894',
  26             'uploader': 'Bluebeat Shelter',
  27         },
  28     }, {
  29         'url': 'https://drooble.com/karl340758/videos/2859183',
  30         'info_dict': {
  31             'id': 'J6QCQY_I5Tk',
  32             'ext': 'mp4',
  33             'title': 'Skankocillin',
  34             'uploader_id': 'UCrSRoI5vVyeYihtWEYua7rg',
  35             'description': 'md5:ffc0bd8ba383db5341a86a6cd7d9bcca',
  36             'upload_date': '20200731',
  37             'uploader': 'Bluebeat Shelter',
  38         },
  39     }, {
  40         'url': 'https://drooble.com/karl340758/music/albums/2858031',
  41         'info_dict': {
  42             'id': '2858031',
  43         },
  44         'playlist_mincount': 8,
  45     }, {
  46         'url': 'https://drooble.com/karl340758/music',
  47         'info_dict': {
  48             'id': 'karl340758',
  49         },
  50         'playlist_mincount': 8,
  51     }, {
  52         'url': 'https://drooble.com/karl340758/videos',
  53         'info_dict': {
  54             'id': 'karl340758',
  55         },
  56         'playlist_mincount': 8,
  57     }]
  58
  59     def _call_api(self, method, video_id, data=None):
  60         response = self._download_json(
  61             f'https://drooble.com/api/dt/{method}', video_id, data=json.dumps(data).encode())
  62         if not response[0]:
  63             raise ExtractorError('Unable to download JSON metadata')
  64         return response[1]
  65
  66     def _real_extract(self, url):
  67         mobj = self._match_valid_url(url)
  68         user = mobj.group('user') or mobj.group('user_2')
  69         kind = mobj.group('kind') or mobj.group('kind_2')
  70         display_id = mobj.group('id') or user
  71
  72         if mobj.group('kind_2') == 'videos':
  73             data = {'from_user': display_id, 'album': -1, 'limit': 18, 'offset': 0, 'order': 'new2old', 'type': 'video'}
  74         elif kind in ('music/albums', 'music'):
  75             data = {'user': user, 'public_only': True, 'individual_limit': {'singles': 1, 'albums': 1, 'playlists': 1}}
  76         else:
  77             data = {'url_slug': display_id, 'children': 10, 'order': 'old2new'}
  78
  79         method = 'getMusicOverview' if kind in ('music/albums', 'music') else 'getElements'
  80         json_data = self._call_api(method, display_id, data=data)
  81         if kind in ('music/albums', 'music'):
  82             json_data = json_data['singles']['list']
  83
  84         entites = []
  85         for media in json_data:
  86             url = media.get('external_media_url') or media.get('link')
  87             if url.startswith('https://www.youtube.com'):
  88                 entites.append({
  89                     '_type': 'url',
  90                     'url': url,
  91                     'ie_key': 'Youtube',
  92                 })
  93                 continue
  94             is_audio = (media.get('type') or '').lower() == 'audio'
  95             entites.append({
  96                 'url': url,
  97                 'id': media['id'],
  98                 'title': media['title'],
  99                 'duration': int_or_none(media.get('duration')),
 100                 'timestamp': int_or_none(media.get('timestamp')),
 101                 'album': try_get(media, lambda x: x['album']['title']),
 102                 'uploader': try_get(media, lambda x: x['creator']['display_name']),
 103                 'uploader_id': try_get(media, lambda x: x['creator']['id']),
 104                 'thumbnail': media.get('image_comment'),
 105                 'like_count': int_or_none(media.get('likes')),
 106                 'vcodec': 'none' if is_audio else None,
 107                 'ext': 'mp3' if is_audio else None,
 108             })
 109
 110         if len(entites) > 1:
 111             return self.playlist_result(entites, display_id)
 112
 113         return entites[0]